OPEN MODELS / AI image generation
Run FLUX.1-dev on a cloud GPU
FLUX.1-dev is a AI image generation model by rayonlabs. See how much GPU memory it needs, which GPUs it fits on today and what it costs to run it yourself, billed per second.
GPUs it fits on today
Our estimate is about 30 GB for inference with BF16 weights, including working memory. Real use depends on resolution, batch size and context length.
| GPU | Memory | Per hour | 10 hours | |
|---|---|---|---|---|
| Q RTX 8000 | 45 GB | $0.48 | $4.80 | Rent |
| A100 SXM4 | 40 GB | $0.67 | $6.70 | Rent |
| RTX 5000Ada | 32 GB | $0.69 | $6.90 | Rent |
| A100 PCIE | 40 GB | $0.74 | $7.40 | Rent |
| CMP 170HX | 64 GB | $0.75 | $7.50 | Rent |
Live starting prices from our catalog. You pay per second while the machine runs.
How to run FLUX.1-dev
- 01
Rent a GPU
Pick one of the GPUs above. Billing is per second; stop the machine and you stop paying.
- 02
Open a terminal or Jupyter
Connect over SSH or open Jupyter in your browser. PyTorch and CUDA are ready to use.
- 03
Download and run the model
Run the commands below. The weights download straight from Hugging Face to your machine.
pip install -U diffusers transformers accelerate
huggingface-cli download rayonlabs/FLUX.1-dev --local-dir ./model
python -c "import torch; from diffusers import DiffusionPipeline; p = DiffusionPipeline.from_pretrained('./model', torch_dtype=torch.bfloat16).to('cuda'); print(p)"Why run it yourself?
With your own GPU there is no monthly plan and no per-image credit. Load any model or LoRA you want and generate in batches.
Questions
- How much GPU memory does FLUX.1-dev need?
- By our estimate about 30 GB for inference (12B parameters). Higher resolution, longer context or bigger batches need more.
- How much does it cost to run FLUX.1-dev?
- From $0.48 per hour on Q RTX 8000, billed per second. Ten hours cost about $4.80.
- Do I need a subscription?
- No. You pay only for the time your machine runs, from your USD balance. Stop it whenever you are done.
Try it on your own GPU in minutes
Pick a GPU, open Jupyter or SSH and run any open model. You pay per second and can stop anytime; no subscription, no setup fee.
- Per-second billing in USD
- PyTorch and CUDA ready in minutes
- Rent from ChatGPT or Claude too